Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile needs no repetition. The description earns credit beyond that by disclosing the actual outputs produced: a hosted PNG link, a share page, alt text, and editable PowerPoint/Excel links — information an agent cannot get from the annotations or the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences in a deliberate order: what it draws, what data it expects, which sibling to use instead, then what it returns. No boilerplate, no redundant restatement of parameters, and the alternative routing is placed before the return-value sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 9 parameters, nested objects and no output schema, the description covers the two things an agent most needs: the input data shape and the return artifacts, plus a sibling escape hatch. Styling parameters (palette, texture, theme, dimensions) are left entirely to the schema, which is acceptable given full coverage, though a note on when brandTheme applies is present only in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter including nested data, style, palette and brandTheme is already documented in structured fields. The description only restates the data element shape and adds the bubble alternative; it adds no syntax or formatting meaning beyond the schema, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb ('Draw') plus resource ('scatter plot') plus the exact data shape ('two numeric measures per item') and the analytical intent ('correlation or clusters'), with a concrete example ('price vs rating'). It also distinguishes itself from the bubble-chart path, so an agent can separate it from generate_more_charts without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear when-to-use signal (showing correlation or clusters between two numeric measures) and an explicit routing rule: sizing dots by a third measure should go to generate_more_charts with type bubble. It stops short of exclusions against adjacent siblings like line or histogram charts, so it is strong but not exhaustive.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.